Extent and Depth of Flooding Using SAR Sentinel-1 and Machine Learning Algorithms

Climate change is causing extreme events to become more and more frequent around the world; In particular, Mexico faces recurring floods with loss of human lives and infrastructure. The objective of this work was to identify the extent and depth of flooded areas using SAR Sentinel-1, DEM, and Random Forest and Logistic Regression algorithms. The Random Forest algorithm achieved better classification metrics over the Logistic Regression algorithm; both with a good performance to identify floods using SAR and DEM images to respond to the contingencies caused by this extreme phenomenon.